Papers with Code 아카이브

Continual Learning

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 5
평가표: 33
보존된 평가 기록: 133

Continual Learning (also known as Incremental Learning, Life-long Learning) is a concept to learn a model for a large number of tasks sequentially without forgetting knowledge obtained from the preceding tasks, where the data in the old tasks are not available anymore during training new ones.
If not mentioned, the benchmarks here are Task-CL, where task-id is provided on validation.

Source:
Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation
Three scenarios for continual learning
Lifelong Machine Learning
Continual lifelong learning with neural networks: A review

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/sergiolib/reproduce_oml

Meta-Learning Representations for Continual Learning

https://github.com/shawnbeaulieu/ANML

Learning to Continually Learn

https://github.com/shivamsaboo17/overcoming-catastrophic-forgetting-in-neural-networks

Overcoming catastrophic forgetting in neural networks

https://github.com/shriramsb/batchRL-SI

Continual Learning Through Synaptic Intelligence

https://github.com/sidtandon2014/fw-shapley

Supervised Contrastive Learning

https://github.com/sjtu-dmtai/onlinetsf

Dark Experience for General Continual Learning: a Strong, Simple Baseline

https://github.com/smidtfab/nba_score_analyzer

Continual Learning in Neural Networks

https://github.com/stevenygd/WAGE.pytorch

Training and Inference with Integers in Deep Neural Networks

https://github.com/stijani/elastic-weight-consolidation-tf2

Overcoming catastrophic forgetting in neural networks

https://github.com/sudhakaranjain/3D_DEN

3D_DEN: Open-ended 3D Object Recognition using Dynamically Expandable Networks

https://github.com/swagshaw/rainbow-keywords

Progressive Continual Learning for Spoken Keyword Spotting

https://github.com/taldatech/tf-bgd

Task Agnostic Continual Learning Using Online Variational Bayes

https://github.com/thejungwon/gc-fed

Preservation of the Global Knowledge by Not-True Distillation in Federated Learning

https://github.com/torchjd/torchjd

Gradient Episodic Memory for Continual Learning

https://github.com/uiuctml/HypStructure

Supervised Contrastive Learning

https://github.com/vgaraujov/lll-nlp

Episodic Memory in Lifelong Language Learning

https://github.com/vijaylee/ALTA

https://github.com/vios-s/adversarial-test-time-training

Re-using Adversarial Mask Discriminators for Test-time Training under Distribution Shifts

https://github.com/vk1996/contrastive_learning

Supervised Contrastive Learning

https://github.com/vlomonaco/ar1-pytorch

Rehearsal-Free Continual Learning over Small Non-I.I.D. Batches

https://github.com/vlomonaco/core50

Rehearsal-Free Continual Learning over Small Non-I.I.D. Batches

https://github.com/wang-ml-lab/unified-continual-learning

A Unified Approach to Domain Incremental Learning with Memory: Theory and Algorithm

https://github.com/wannabeOG/ExpertNet-Pytorch

Learning without Forgetting

https://github.com/wannabeOG/MAS-PyTorch

Overcoming catastrophic forgetting in neural networks

https://github.com/wuzhiyuan2000/FedAgg

Federated Class-Incremental Learning with New-Class Augmented Self-Distillation

https://github.com/wyatuestc/overcoming-catastrophic

Overcoming catastrophic forgetting in neural networks

https://github.com/xujinfan/Reinforced-Continual-Learning

Reinforced Continual Learning

https://github.com/xyutao/fscil

Few-Shot Class-Incremental Learning

https://github.com/yangyucheng000/MSpaper/tree/main/tsn

Task-Specific Normalization for Continual Learning of Blind Image Quality Models

https://github.com/yanyansann/prompttpp

Prompt-augmented Temporal Point Process for Streaming Event Sequence

https://github.com/yixinghuang/deepmedicpytorch

A Survey of Incremental Transfer Learning: Combining Peer-to-Peer Federated Learning and Domain Incremental Learning for Multicenter Collaboration

https://github.com/yuz1wan/video_distillation

Dataset Condensation with Gradient Matching

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.